turboderp-org/exllamav3
1
0
Fork 0
mirror of https://github.com/turboderp-org/exllamav3.git synced 2026-05-11 16:30:12 +00:00
Code Issues Packages Projects Releases Wiki Activity
787 Commits 3 Branches 34 Tags
863f96bcaec2c134a733871c550f8a58db93e97c
Commit Graph

9 Commits

Author SHA1 Message Date
turboderp
3634436641 model_diff.py: Limit batch size (prevent OoM on output layer) 2025-10-29 21:15:35 +01:00
turboderp
5cb70f591b model_diff.py: Add option to save IDs and logits 2025-07-15 20:34:10 +02:00
turboderp
6341b119ef Loader: Add tensor override script 2025-07-08 18:58:43 +02:00
turboderp
2cc8f718da Add cosine_error and SQNR measures 2025-05-30 19:43:20 +02:00
turboderp
f8dc9975fe model_diff.py: Add device argument 2025-05-30 19:42:49 +02:00
turboderp
5c3ff204c4 model_diff.py: Use deferred load and close file handles between modules 2025-05-12 21:23:48 +02:00
turboderp
9575f7d8b2 model_diff.py: Add KLD and top-K test to 2025-05-06 20:23:47 +02:00
turboderp
25d9388bce model_diff.py: Add option to start eval from any layer 2025-04-17 11:44:05 +02:00
turboderp
543c4b2771 Initial commit 2025-04-06 14:42:49 +02:00